Best Claude skills for Coding
Coding skills change how your agent works, not only what it writes: brainstorm before building, write a plan, test first, review its own diff, and finish branches cleanly. Packs like Superpowers, Matt Pocock's skills, Addy Osmani's agent skills and Garry Tan's gstack are the most starred skills on GitHub.
1747 coding skills · ranked nightly · November 2026
The top 10. Ranked by the Alyn Score.
- 1#1
Matt Pocock
Code Review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code…
Pack321k33MScore 98 - 2#2
Codebase Design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more…
Pack321k33MScore 98 - 3#3
Diagnosing Bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Pack321k33MScore 98 - 4#4
JuliusBrussee
Caveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or…
Pack119k4.8MScore 93 - 5#5
Caveman Commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
Pack119k4.8MScore 93 - 6#6
Caveman Learn
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's…
Pack119k4.8MScore 93 - 7#7
morluto
Rea Analysis Optimization
Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query…
Pack450k29kScore 93 - 8#8
Rea Ci Tests Audit
Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary…
Pack450k29kScore 93 - 9#9
Jesse Vincent
Superpowers
Jesse Vincent
Brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a…
Pack316k3.9MScore 92 - 10#10
Jesse Vincent
Superpowers
Diagnosing Superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why…
Pack316k3.9MScore 92
What makes a great coding skill.
A workflow (plan, implement, verify) rather than a list of tips.
Explicit stop conditions so the agent asks instead of guessing.
Skills that compose: planning, testing and review that hand off to each other.
All 1747 coding skills.
jeremylongshorequit-sponsor
Turns an AI agent with persistent memory into a quit-smoking sponsor. Use when a person asks for help quitting smoking (cigarettes or other smoked tobacco), announces they are quitting…
kangarookingrational-buddhism
当用户问某主张/玄学/灵修该不该信、想建立自己的验证标准、或寻找科学与精神的结合点时调用。 核心理念: 尝试一切, 亲自测试, 保持怀疑, 保留有用的, 舍弃没用的; 不可证伪的主张不进入基本真理; 冥想/接纳等内在技术可保留。 不适用于: 需要信仰安慰的临终/哀伤场景(尊重个体选择)。 Triggers: 该不该信/玄学/灵修/冥想/可证伪/验证/理性/rational…
kangarookingreading-metaskill
当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单/reading/how to learn
jeremylongshorereasoning
Use BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what…
kangarookingscreen-detox
当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。 核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。 不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/screen…
kangarookingself-liberation
当用户被别人的期望压垮、容易愤怒、或感觉被工作/责任困住、问「怎么说不/怎么不生气/怎么更自由」时调用。 核心理念: 期望不是你的合同(约定才是); 愤怒是自我惩罚; 就业自由来自低生活成本; 自由=免于被迫反应的自由。 不适用于: 违约/欠债等真正的约定责任。 Triggers: 期望/愤怒/自由/取悦别人/说不/就业自由/freedom/anger/expectations
tech-leads-clubtechnical-design-doc-creator
Creates comprehensive Technical Design Documents (TDD) with mandatory and optional sections through interactive discovery. Use when user asks to "write a design doc", "create a TDD"…
BuilderIOvisual-recap
Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.
kangarookingwealth-structure
当用户问「怎么赚钱/如何致富/该不该要期权/如何判断一个生意的结构」时调用。 核心理念: 财富=睡觉时仍在赚钱的资产; 靠「责任(押上声誉)→产权(股权/知识产权)→杠杆(无需许可的代码媒体)→避免出局」构建, 无法靠出租时间致富。 不适用于: 具体投资标的分析、理财产品的选股建议。 Triggers: 致富/赚钱/股权/期权/杠杆/被动…
BuilderIOwebmcp
Open a user-provided URL in the host's built-in browser and use the page's MCP or WebMCP tools before browser UI automation for app communication or edits.
mohitagw15856agent-era-pricing
Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or…
mohitagw15856agent-hiring-panel
Hire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview run on your real tasks, reference checks (what do actual users…
mohitagw15856agent-kill-switch-plan
Prepare, before you need it, the runbook for stopping a proactive agent that is misbehaving: how to pause it in seconds, which connections to revoke in what order, how to check what it did…
mohitagw15856agent-negotiation-brief
Brief an AI agent that will negotiate for you with another party's agent or a person (a refund, a price, a meeting time, a contract term): your goal, your opening, your limits, your…
mohitagw15856agent-observability-spec
Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what to log for an LLM app, design agent tracing or spans, define quality and cost…
mohitagw15856agent-project-file
Set up the project file an AI agent keeps for work that runs over days or weeks: the goal, the definition of done, milestones, the current state, decisions made, open questions, and the…
mohitagw15856agent-readiness-audit
Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is…
mohitagw15856agent-severance
Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the handover…
mohitagw15856agent-spec
Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write…
mohitagw15856aging-in-place-assessment
Assess whether and how someone can safely stay in their own home as they age — the home hazards, the support gaps, and the modifications and services that make it work. Use when asked can…
mohitagw15856aging-parent-talks
Prepare the conversations with aging parents that everyone postpones — the driving talk, the money talk, the care-options talk, the moving talk — each with an opener that doesn't ambush, a…
mohitagw15856agm-in-a-box
Run a club, PTA, or association AGM that finishes on time and holds up later — the notice and agenda done right, a quorum plan, minutes that capture decisions not conversations, elections…
dzhngaudit-decisions
Audit the decisions an implementing agent made, not its diff — a pure audit that traces the session's history into a decisions ledger, changes no code, and never blocks an unsupervised run…
dzhngaudit-performance
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling…
dzhngclose-spec
When a spec under specs// is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable…
dzhngcodex
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as…
muratcankoylanharness-engineering
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR…
dzhngimplement-spec
Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat…
dzhngimplement-spec-with-codex
Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with…
internet-court
Internet Court Skill
internet-courtnla-create
Create a Natural Language Agreement escrow on-chain. Use when the user wants to lock ERC20 tokens in an escrow with a natural language demand that an AI oracle will arbitrate. Handles…
internet-court
Internet Court Skill
internet-courtnla-fulfill
Fulfill an existing NLA escrow and collect tokens. Use when the user wants to submit fulfillment text for an on-chain escrow, check arbitration results, and collect approved funds. Covers…
dzhngrenderer
Architecture rules for GPU rendering with TypeGPU/WebGPU. Use when adding or changing render passes, shaders, frame orchestration, GPU resources, culling, terrain, shadows, or visual…
waynesutton
Builder Skills
waynesuttonthink-first
Reflection first problem solving for Convex projects: root cause before code, two candidate fixes, a 98 percent confidence bar, and changes limited to the files the request needs. Use…
waynesutton
Builder Skills
waynesuttonupdate-project-docs
Brings task.md, changelog.md, and files.md back in sync with what the code says shipped, then prints a commit message as plain text. Reads git history and the working tree, never memory…
Addy Osmani
Web Quality Skills
Addy Osmaniweb-quality-audit
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run…
dzhngwrite-spec
Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API…
Coding skills, explained.
Also searched as: claude code skills, best claude code skills, software engineering skills, superpowers.
What are the best Claude skills for coding?
Right now the top-ranked coding skills on Alyn are Code Review (Matt Pocock), Codebase Design (Matt Pocock), Diagnosing Bugs (Matt Pocock). Rankings combine popularity, quality checks, momentum and freshness, and update every night.
What are the best Claude Code skills?
By stars and installs: Superpowers (obra), Matt Pocock's skills, Addy Osmani's agent-skills, gstack (Garry Tan) and Caveman. Alyn ranks them live.
How many skills should I install?
Start with one workflow pack and two or three task skills. Each skill only costs about 100 tokens until it is used, but overlapping skills can confuse which one runs.
How do I install a coding skill?
Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.
More in Build
Coding skills for your agent